Indonesia Conference Directory

Abstract - The image has the features of shape, color and texture that are vary. Each feature has adifferent performance in supporting the accuracy of information retrieval using a processapproach to CBIR (Content-Based Image Retrieval). On the image with different objectsdifferent erformance will be generated on each feature. For example that the performancefeatures of the form of the more dominant compared features color and texture on the image with the face, while the object on the image with the object of interest feature is moredominant than the features of texture and shape.In this research was conducted on theanalysis of the performance features of the shape, color and texture in supporting theaccuracy of a search using the approach of CBIR (Content Based Image Retrieval). Themethod used are invariant moment, color moment and GLCM ( Grey Level Co-occurrenceMatrix). The results showed that the best search accuracy is 95%, where the features ofshape has a performance by 50%, 30% color feature and texture feature by 20% with 600test image with object database assets Keywords : Performance, Feature, Retrieval,